python
Linkup is world's best search for AI applications
claude mcp add --transport stdio linkupplatform-python-mcp-server python -m linkup_mcp_server \ --env LINKUP_API_KEY="API key for Linkup services"
How to use
This MCP server exposes web search capabilities through Linkup's search API, enabling AI assistants and development tools to perform natural language queries and retrieve up-to-date web results with source citations. By running the server with the Linkup API key, clients can send MCP requests to perform searches, get structured results, and navigate through sources. The server is designed to work with any MCP-compatible client, so you can integrate it into your assistant, IDE plugins, or other tooling that uses the MCP protocol. When deploying, ensure the LINKUP_API_KEY environment variable is set so the server can authenticate with Linkup's services. You can then configure your MCP client to connect to the host and port where this Python server is running and start issuing search queries or related MCP actions as supported by the protocol.
How to install
Prerequisites:
- Python 3.8+ installed on the system
- Access to the internet to install dependencies
Installation steps:
-
Create and activate a virtual environment (recommended): python3 -m venv venv source venv/bin/activate # Linux/macOS venv\Scripts\activate.bat # Windows
-
Install the Linkup MCP server package: pip install linkup-mcp-server # or the appropriate package name if different
-
Set the required environment variable (obtain an API key from Linkup): export LINKUP_API_KEY=your_api_key_here # Linux/macOS set LINKUP_API_KEY=your_api_key_here # Windows
-
Run the MCP server using the Python module entry point: python -m linkup_mcp_server
-
Verify the server starts and is reachable by your MCP client using the configured host/port.
Note: If you are packaging this for deployment, ensure the environment variable is securely provided through your hosting environment (e.g., container secrets, environment config).
Additional notes
Note: This Python MCP server is deprecated in favor of the TypeScript/Node.js version. If you require ongoing maintenance and feature parity, consider migrating to the TypeScript implementation at the recommended repository. Common issues may include missing or invalid API keys, network restrictions preventing access to Linkup services, or mismatched MCP client configurations. Ensure the environment variable LINKUP_API_KEY is set in the deployment environment and that the server has outbound access to Linkup APIs. If you encounter authentication errors, double-check the API key scope and permissions. For debugging, consult the server logs for MCP requests and responses to confirm proper protocol handling.
Related MCP Servers
claude-talk-to-figma
A Model Context Protocol (MCP) that allows Claude Desktop and other AI tools (Claude Code, Cursor, Antigravity, etc.) to read, analyze, and modify Figma designs
skillport
Bring Agent Skills to Any AI Agent and Coding Agent — via CLI or MCP. Manage once, serve anywhere.
cursor-notebook
Model Context Protocol (MCP) server designed to allow AI agents within Cursor to interact with Jupyter Notebook (.ipynb) files
example
A ready-to-use MCP (Model Context Protocol) server template for extending Cursor IDE with custom tools. Deploy your own server to Heroku with one click, create custom commands, and enhance your Cursor IDE experience. Perfect for developers who want to add their own tools and commands to Cursor IDE without complex setup.
claude_autoapprove_mcp
An MCP server to inject auto-approve MCP functionality into Claude Desktop
mcp-simple-timeserver
Simple MCP to give Claude ability to check current time as well as know when holidays are, what is the time distance between dates etc.